Arxiv:1910.09700 Autotrain compatible Dataset:alivi/qaspanish En Endpoints compatible Es Lora Mistral Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/alivi/fine-tuning_Zephyr-7b_SpanishQA
Fine Tuning Zephyr 7b SpanishQA Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Fine Tuning Zephyr 7B SpanishQA Parameters and Internals
| LLM Name | Fine Tuning Zephyr 7b SpanishQA |
| Repository 🤗 | https://huggingface.co/alivi/fine-tuning_Zephyr-7b_SpanishQA |
| Model Size | 7b |
| Required VRAM | 0.1 GB |
| Updated | 2025-02-17 |
| Maintainer | alivi |
| Model Files | |
| Supported Languages | en es |
| Model Architecture | AutoModelForCausalLM |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.1 |
| R Param | 64 |
Best Alternatives to Fine Tuning Zephyr 7B SpanishQA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 566357 | 1388 |
| Mistral 7B V0.3 | 32K / 14.5 GB | 179293 | 438 |
| Mistral 7B V0.3 | 32K / 14.5 GB | 4736 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 4052 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 1045 | 3 |
| ...unoichi Lemon Royale V3 32K 7B | 32K / 14.5 GB | 26 | 4 |
| Mistralai Mistral 7B V0.3 | 32K / 14.5 GB | 25 | 3 |
| ...ralai Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 27 | 1 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 5 | 0 |
| Mistral 7B V0.2 | 32K / 14.5 GB | 20 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than alivi/fine-tuning_Zephyr-7b_SpanishQA .
Rank the Fine Tuning Zephyr 7B SpanishQA Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227